references.bib

@article{anon2023sup,
    author = {Anonymous},
    title = {Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models},
    year = {2023},
    journal={Anonymous Journal}
}

@article{avola2021ultrasound,
  title={Ultrasound medical imaging techniques: a survey},
  author={Avola, Danilo and Cinque, Luigi and Fagioli, Alessio and Foresti, Gianluca and Mecca, Alessio},
  journal={ACM Computing Surveys (CSUR)},
  volume={54},
  number={3},
  pages={1--38},
  year={2021},
  publisher={ACM New York, NY, USA}
}

@article{chen2021transunet,
  title={Transunet: Transformers make strong encoders for medical image segmentation},
  author={Chen, Jieneng and Lu, Yongyi and Yu, Qihang and Luo, Xiangde and Adeli, Ehsan and Wang, Yan and Lu, Le and Yuille, Alan L and Zhou, Yuyin},
  journal={arXiv preprint arXiv:2102.04306},
  year={2021}
}

@article{chen2023towards,
  title={Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts},
  author={Chen, Zhihong and Diao, Shizhe and Wang, Benyou and Li, Guanbin and Wan, Xiang},
  journal={arXiv preprint arXiv:2302.08958},
  year={2023}
}

@inproceedings{deng2021transbridge,
  title={TransBridge: A lightweight transformer for left ventricle segmentation in echocardiography},
  author={Deng, Kaizhong and Meng, Yanda and Gao, Dongxu and Bridge, Joshua and Shen, Yaochun and Lip, Gregory and Zhao, Yitian and Zheng, Yalin},
  booktitle={Simplifying Medical Ultrasound: Second International Workshop, ASMUS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings 2},
  pages={63--72},
  year={2021},
  organization={Springer}
}

@inproceedings{do2021multiple,
  title={Multiple meta-model quantifying for medical visual question answering},
  author={Do, Tuong and Nguyen, Binh X and Tjiputra, Erman and Tran, Minh and Tran, Quang D and Nguyen, Anh},
  booktitle={Medical Image Computing and Computer Assisted Intervention--MICCAI 2021: 24th International Conference, Strasbourg, France, September 27--October 1, 2021, Proceedings, Part V 24},
  pages={64--74},
  year={2021},
  organization={Springer}
}

@article{dosovitskiy2020image,
  title={An image is worth 16x16 words: Transformers for image recognition at scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
  journal={arXiv preprint arXiv:2010.11929},
  year={2020}
}

@article{furst2022cloob,
  title={Cloob: Modern hopfield networks with infoloob outperform clip},
  author={F{\"u}rst, Andreas and Rumetshofer, Elisabeth and Lehner, Johannes and Tran, Viet T and Tang, Fei and Ramsauer, Hubert and Kreil, David and Kopp, Michael and Klambauer, G{\"u}nter and Bitto, Angela and others},
  journal={Advances in neural information processing systems},
  volume={35},
  pages={20450--20468},
  year={2022}
}

@article{goodfellow2014generative,
  title={Generative adversarial nets},
  author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  journal={Advances in neural information processing systems},
  volume={27},
  year={2014}
}

@inproceedings{hatamizadeh2021swin,
  title={Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images},
  author={Hatamizadeh, Ali and Nath, Vishwesh and Tang, Yucheng and Yang, Dong and Roth, Holger R and Xu, Daguang},
  booktitle={International MICCAI Brainlesion Workshop},
  pages={272--284},
  year={2021},
  organization={Springer}
}

@inproceedings{hatamizadeh2022unetr,
  title={Unetr: Transformers for 3d medical image segmentation},
  author={Hatamizadeh, Ali and Tang, Yucheng and Nath, Vishwesh and Yang, Dong and Myronenko, Andriy and Landman, Bennett and Roth, Holger R and Xu, Daguang},
  booktitle={Proceedings of the IEEE/CVF winter conference on applications of computer vision},
  pages={574--584},
  year={2022}
}

@article{havaei2017brain,
  title={Brain tumor segmentation with deep neural networks},
  author={Havaei, Mohammad and Davy, Axel and Warde-Farley, David and Biard, Antoine and Courville, Aaron and Bengio, Yoshua and Pal, Chris and Jodoin, Pierre-Marc and Larochelle, Hugo},
  journal={Medical image analysis},
  volume={35},
  pages={18--31},
  year={2017},
  publisher={Elsevier}
}

@article{ho2020denoising,
  title={Denoising diffusion probabilistic models},
  author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={6840--6851},
  year={2020}
}

@article{huang2020pixel,
  title={Pixel-bert: Aligning image pixels with text by deep multi-modal transformers},
  author={Huang, Zhicheng and Zeng, Zhaoyang and Liu, Bei and Fu, Dongmei and Fu, Jianlong},
  journal={arXiv preprint arXiv:2004.00849},
  year={2020}
}

@article{isensee2021nnu,
  title={nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation},
  author={Isensee, Fabian and Jaeger, Paul F and Kohl, Simon AA and Petersen, Jens and Maier-Hein, Klaus H},
  journal={Nature methods},
  volume={18},
  number={2},
  pages={203--211},
  year={2021},
  publisher={Nature Publishing Group US New York}
}

@inproceedings{jia2021scaling,
  title={Scaling up visual and vision-language representation learning with noisy text supervision},
  author={Jia, Chao and Yang, Yinfei and Xia, Ye and Chen, Yi-Ting and Parekh, Zarana and Pham, Hieu and Le, Quoc and Sung, Yun-Hsuan and Li, Zhen and Duerig, Tom},
  booktitle={International Conference on Machine Learning},
  pages={4904--4916},
  year={2021},
  organization={PMLR}
}

@article{kingma2014adam,
  title={Adam: A method for stochastic optimization},
  author={Kingma, Diederik P and Ba, Jimmy},
  journal={arXiv preprint arXiv:1412.6980},
  year={2014}
}

@article{leclerc2019deep,
  title={Deep learning for segmentation using an open large-scale dataset in 2D echocardiography},
  author={Leclerc, Sarah and Smistad, Erik and Pedrosa, Joao and {\O}stvik, Andreas and Cervenansky, Frederic and Espinosa, Florian and Espeland, Torvald and Berg, Erik Andreas Rye and Jodoin, Pierre-Marc and Grenier, Thomas and others},
  journal={IEEE transactions on medical imaging},
  volume={38},
  number={9},
  pages={2198--2210},
  year={2019},
  publisher={IEEE}
}

@article{li2021supervision,
  title={Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm},
  author={Li, Yangguang and Liang, Feng and Zhao, Lichen and Cui, Yufeng and Ouyang, Wanli and Shao, Jing and Yu, Fengwei and Yan, Junjie},
  journal={arXiv preprint arXiv:2110.05208},
  year={2021}
}

@inproceedings{li2022blip,
  title={Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation},
  author={Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
  booktitle={International Conference on Machine Learning},
  pages={12888--12900},
  year={2022},
  organization={PMLR}
}

@inproceedings{li2022grounded,
  title={Grounded language-image pre-training},
  author={Li, Liunian Harold and Zhang, Pengchuan and Zhang, Haotian and Yang, Jianwei and Li, Chunyuan and Zhong, Yiwu and Wang, Lijuan and Yuan, Lu and Zhang, Lei and Hwang, Jenq-Neng and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10965--10975},
  year={2022}
}

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
  booktitle={Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13},
  pages={740--755},
  year={2014},
  organization={Springer}
}

@inproceedings{ling2022reaching,
  title={Reaching intra-observer variability in 2-D echocardiographic image segmentation with a simple U-Net architecture},
  author={Ling, Hang Jung and Garcia, Damien and Bernard, Olivier},
  booktitle={IEEE International Ultrasonics Symposium (IUS)},
  year={2022}
}

@article{loshchilov2017decoupled,
  title={Decoupled weight decay regularization},
  author={Loshchilov, Ilya and Hutter, Frank},
  journal={arXiv preprint arXiv:1711.05101},
  year={2017}
}

@inproceedings{luddecke2022image,
  title={Image segmentation using text and image prompts},
  author={L{\"u}ddecke, Timo and Ecker, Alexander},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={7086--7096},
  year={2022}
}

@inproceedings{milletari2016v,
  title={V-net: Fully convolutional neural networks for volumetric medical image segmentation},
  author={Milletari, Fausto and Navab, Nassir and Ahmadi, Seyed-Ahmad},
  booktitle={2016 fourth international conference on 3D vision (3DV)},
  pages={565--571},
  year={2016},
  organization={Ieee}
}

@article{oktay2018attention,
  title={Attention u-net: Learning where to look for the pancreas},
  author={Oktay, Ozan and Schlemper, Jo and Folgoc, Loic Le and Lee, Matthew and Heinrich, Mattias and Misawa, Kazunari and Mori, Kensaku and McDonagh, Steven and Hammerla, Nils Y and Kainz, Bernhard and others},
  journal={arXiv preprint arXiv:1804.03999},
  year={2018}
}

@inproceedings{patashnik2021styleclip,
  title={Styleclip: Text-driven manipulation of stylegan imagery},
  author={Patashnik, Or and Wu, Zongze and Shechtman, Eli and Cohen-Or, Daniel and Lischinski, Dani},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={2085--2094},
  year={2021}
}

@inproceedings{plummer2015flickr30k,
  title={Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models},
  author={Plummer, Bryan A and Wang, Liwei and Cervantes, Chris M and Caicedo, Juan C and Hockenmaier, Julia and Lazebnik, Svetlana},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={2641--2649},
  year={2015}
}

@article{qin2022medical,
  title={Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study},
  author={Qin, Ziyuan and Yi, Huahui and Lao, Qicheng and Li, Kang},
  journal={arXiv preprint arXiv:2209.15517},
  year={2022}
}

@inproceedings{radford2021learning,
  title={Learning transferable visual models from natural language supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
  booktitle={International conference on machine learning},
  pages={8748--8763},
  year={2021},
  organization={PMLR}
}

@inproceedings{rao2022denseclip,
  title={Denseclip: Language-guided dense prediction with context-aware prompting},
  author={Rao, Yongming and Zhao, Wenliang and Chen, Guangyi and Tang, Yansong and Zhu, Zheng and Huang, Guan and Zhou, Jie and Lu, Jiwen},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={18082--18091},
  year={2022}
}

@inproceedings{ronneberger2015u,
  title={U-net: Convolutional networks for biomedical image segmentation},
  author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
  booktitle={Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18},
  pages={234--241},
  year={2015},
  organization={Springer}
}

@article{schuhmann2022laion,
  title={Laion-5b: An open large-scale dataset for training next generation image-text models},
  author={Schuhmann, Christoph and Beaumont, Romain and Vencu, Richard and Gordon, Cade and Wightman, Ross and Cherti, Mehdi and Coombes, Theo and Katta, Aarush and Mullis, Clayton and Wortsman, Mitchell and others},
  journal={arXiv preprint arXiv:2210.08402},
  year={2022}
}

@inproceedings{seibold2022breaking,
  title={Breaking with fixed set pathology recognition through report-guided contrastive training},
  author={Seibold, Constantin and Rei{\ss}, Simon and Sarfraz, M Saquib and Stiefelhagen, Rainer and Kleesiek, Jens},
  booktitle={Medical Image Computing and Computer Assisted Intervention--MICCAI 2022: 25th International Conference, Singapore, September 18--22, 2022, Proceedings, Part V},
  pages={690--700},
  year={2022},
  organization={Springer}
}

@inproceedings{sharma2018conceptual,
  title={Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning},
  author={Sharma, Piyush and Ding, Nan and Goodman, Sebastian and Soricut, Radu},
  booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={2556--2565},
  year={2018}
}

@inproceedings{singh2022flava,
  title={Flava: A foundational language and vision alignment model},
  author={Singh, Amanpreet and Hu, Ronghang and Goswami, Vedanuj and Couairon, Guillaume and Galuba, Wojciech and Rohrbach, Marcus and Kiela, Douwe},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={15638--15650},
  year={2022}
}

@article{stojanovski2023echo,
  title={Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation},
  author={Stojanovski, David and Hermida, Uxio and Lamata, Pablo and Beqiri, Arian and Gomez, Alberto},
  journal={arXiv preprint arXiv:2305.05424},
  year={2023}
}

@inproceedings{tomar2022tganet,
  title={TGANet: text-guided attention for improved polyp segmentation},
  author={Tomar, Nikhil Kumar and Jha, Debesh and Bagci, Ulas and Ali, Sharib},
  booktitle={Medical Image Computing and Computer Assisted Intervention--MICCAI 2022: 25th International Conference, Singapore, September 18--22, 2022, Proceedings, Part III},
  pages={151--160},
  year={2022},
  organization={Springer}
}

@inproceedings{wang2022cris,
  title={Cris: Clip-driven referring image segmentation},
  author={Wang, Zhaoqing and Lu, Yu and Li, Qiang and Tao, Xunqiang and Guo, Yandong and Gong, Mingming and Liu, Tongliang},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={11686--11695},
  year={2022}
}

@article{wang2022medclip,
  title={Medclip: Contrastive learning from unpaired medical images and text},
  author={Wang, Zifeng and Wu, Zhenbang and Agarwal, Dinesh and Sun, Jimeng},
  journal={arXiv preprint arXiv:2210.10163},
  year={2022}
}

@inproceedings{wang2022ofa,
  title={Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework},
  author={Wang, Peng and Yang, An and Men, Rui and Lin, Junyang and Bai, Shuai and Li, Zhikang and Ma, Jianxin and Zhou, Chang and Zhou, Jingren and Yang, Hongxia},
  booktitle={International Conference on Machine Learning},
  pages={23318--23340},
  year={2022},
  organization={PMLR}
}

@article{wang2022semantic,
  title={Semantic image synthesis via diffusion models},
  author={Wang, Weilun and Bao, Jianmin and Zhou, Wengang and Chen, Dongdong and Chen, Dong and Yuan, Lu and Li, Houqiang},
  journal={arXiv preprint arXiv:2207.00050},
  year={2022}
}

@inproceedings{wazir2022histoseg,
  title={HistoSeg: Quick attention with multi-loss function for multi-structure segmentation in digital histology images},
  author={Wazir, Saad and Fraz, Muhammad Moazam},
  booktitle={2022 12th International Conference on Pattern Recognition Systems (ICPRS)},
  pages={1--7},
  year={2022},
  organization={IEEE}
}

@incollection{wilcoxon1992individual,
  title={Individual comparisons by ranking methods},
  author={Wilcoxon, Frank},
  booktitle={Breakthroughs in Statistics: Methodology and Distribution},
  pages={196--202},
  year={1992},
  publisher={Springer}
}

@article{wu2023medklip,
  title={MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training},
  author={Wu, Chaoyi and Zhang, Xiaoman and Zhang, Ya and Wang, Yanfeng and Xie, Weidi},
  journal={medRxiv},
  pages={2023--01},
  year={2023},
  publisher={Cold Spring Harbor Laboratory Press}
}

@article{yuksekgonul2022and,
  title={When and why vision-language models behave like bag-of-words models, and what to do about it?},
  author={Yuksekgonul, Mert and Bianchi, Federico and Kalluri, Pratyusha and Jurafsky, Dan and Zou, James},
  journal={arXiv preprint arXiv:2210.01936},
  year={2022}
}

@inproceedings{zhai2022lit,
  title={Lit: Zero-shot transfer with locked-image text tuning},
  author={Zhai, Xiaohua and Wang, Xiao and Mustafa, Basil and Steiner, Andreas and Keysers, Daniel and Kolesnikov, Alexander and Beyer, Lucas},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={18123--18133},
  year={2022}
}

@article{zhang2020contrastive,
  title={Contrastive learning of medical visual representations from paired images and text (2020)},
  author={Zhang, Yuhao and Jiang, Hang and Miura, Yasuhide and Manning, Christopher D and Langlotz, Curtis P},
  journal={arXiv preprint arXiv:2010.00747},
  year={2020}
}

@article{zhang2023large,
  title={Large-Scale Domain-Specific Pretraining for Biomedical Vision-Language Processing},
  author={Zhang, Sheng and Xu, Yanbo and Usuyama, Naoto and Bagga, Jaspreet and Tinn, Robert and Preston, Sam and Rao, Rajesh and Wei, Mu and Valluri, Naveen and Wong, Cliff and others},
  journal={arXiv preprint arXiv:2303.00915},
  year={2023}
}

@inproceedings{zhou2018unet++,
  title={Unet++: A nested u-net architecture for medical image segmentation},
  author={Zhou, Zongwei and Rahman Siddiquee, Md Mahfuzur and Tajbakhsh, Nima and Liang, Jianming},
  booktitle={Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4},
  pages={3--11},
  year={2018},
  organization={Springer}
}

@article{zhou2022zegclip,
  title={ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation},
  author={Zhou, Ziqin and Zhang, Bowen and Lei, Yinjie and Liu, Lingqiao and Liu, Yifan},
  journal={arXiv preprint arXiv:2212.03588},
  year={2022}
}
@inproceedings{zou2023generalized,
  title={Generalized decoding for pixel, image, and language},
  author={Zou, Xueyan and Dou, Zi-Yi and Yang, Jianwei and Gan, Zhe and Li, Linjie and Li, Chunyuan and Dai, Xiyang and Behl, Harkirat and Wang, Jianfeng and Yuan, Lu and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={15116--15127},
  year={2023}
}